VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning
NeurIPSSpotlight2025
TL;DR
Recently, slow-thinking systems like GPT-o1 and DeepSeek-R1 have demonstrated great potential in solving challenging problems through explicit reflection…
Opening excerpt from the authors’ abstract. source
Read the paper
Topics
reinforcement learning vision-language language model
← All NeurIPS 2025 Spotlight papers · Browse the whole archive